amsminn/vericontext
Deterministic, hash-based verification for docs that reference code. Fail-closed. Zero fuzzy matching.
Embeds SHA-256 hashes into invisible HTML comment citations within Markdown docs, enabling bit-exact verification that code snippets haven't drifted. Citations use a fail-closed design—any hash mismatch causes the entire document to fail verification, with no fuzzy matching or approximation. Integrates with 40+ AI agents (Claude Code, Cursor, Windsurf, etc.) via the Skills ecosystem, and exposes three core operations (`cite`, `claim`, `verify workspace`) through both CLI and MCP server for CI/CD pipelines and pre-commit hooks.
Available on npm.
Stars
7
Forks
—
Language
TypeScript
License
MIT
Category
Last pushed
Mar 03, 2026
Commits (30d)
0
Dependencies
3
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/amsminn/vericontext"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Featured in
Higher-rated alternatives
microsoft/agent-governance-toolkit
AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and...
ucsandman/DashClaw
🛡️Decision infrastructure for AI agents. Intercept actions, enforce guard policies, require...
vstorm-co/pydantic-ai-middleware
Middleware layer for Pydantic AI — intercept, transform & guard agent calls with 7 lifecycle...
mattijsmoens/sovereign-shield
AI security framework: tamper-proof action auditing, prompt injection firewall, ethical...
vstorm-co/pydantic-ai-shields
Guardrail capabilities for Pydantic AI — cost tracking, prompt injection detection, PII...